Markov-Switching Linked Autoregressive Model for Non-continuous Wind Direction Data

Xiaoping Zhan, Tiefeng Ma, Shuangzhe Liu, Kunio Shimizu

Research output: Contribution to journalArticle

Abstract

In this paper, a Markov-switching linked autoregressive model is proposed to describe and forecast non-continuous wind direction data. Due to the influence factors of geography and atmosphere, the distribution of wind direction is disjunct and multi-modal. Moreover, for a number of practical situations, wind direction is a time series and its dependence on time provides very important information for modeling. Our model takes these two points into account to give an accurate prediction of this kind of wind direction. A simulation study shows that our model has a significantly higher prediction accuracy and a smaller mean circular prediction error than three existing models and it is illustrated to be effective by analyzing real data. Supplementary materials accompanying this paper appear online.

Original languageEnglish
Pages (from-to)410-425
Number of pages16
JournalJournal of Agricultural, Biological, and Environmental Statistics
Volume23
Issue number3
DOIs
Publication statusPublished - 1 Sep 2018

Fingerprint

Markov Switching
wind direction
Autoregressive Model
prediction
Geography
Prediction
Prediction Error
Atmosphere
Forecast
Time series
geography
Simulation Study
Model
time series
time series analysis
Direction compound
Autoregressive model
Markov switching
atmosphere
Modeling

Cite this

@article{e98a2a0ce6cf47578dd7828f5c964982,
title = "Markov-Switching Linked Autoregressive Model for Non-continuous Wind Direction Data",
abstract = "In this paper, a Markov-switching linked autoregressive model is proposed to describe and forecast non-continuous wind direction data. Due to the influence factors of geography and atmosphere, the distribution of wind direction is disjunct and multi-modal. Moreover, for a number of practical situations, wind direction is a time series and its dependence on time provides very important information for modeling. Our model takes these two points into account to give an accurate prediction of this kind of wind direction. A simulation study shows that our model has a significantly higher prediction accuracy and a smaller mean circular prediction error than three existing models and it is illustrated to be effective by analyzing real data. Supplementary materials accompanying this paper appear online.",
keywords = "Circular regressive model, Mean circular prediction error, Non-continuous wind direction, Prediction accuracy",
author = "Xiaoping Zhan and Tiefeng Ma and Shuangzhe Liu and Kunio Shimizu",
year = "2018",
month = "9",
day = "1",
doi = "10.1007/s13253-018-0331-z",
language = "English",
volume = "23",
pages = "410--425",
journal = "Journal of Agricultural, Biological, and Environmental Statistics",
issn = "1085-7117",
publisher = "Springer",
number = "3",

}

Markov-Switching Linked Autoregressive Model for Non-continuous Wind Direction Data. / Zhan, Xiaoping; Ma, Tiefeng; Liu, Shuangzhe; Shimizu, Kunio.

In: Journal of Agricultural, Biological, and Environmental Statistics, Vol. 23, No. 3, 01.09.2018, p. 410-425.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Markov-Switching Linked Autoregressive Model for Non-continuous Wind Direction Data

AU - Zhan, Xiaoping

AU - Ma, Tiefeng

AU - Liu, Shuangzhe

AU - Shimizu, Kunio

PY - 2018/9/1

Y1 - 2018/9/1

N2 - In this paper, a Markov-switching linked autoregressive model is proposed to describe and forecast non-continuous wind direction data. Due to the influence factors of geography and atmosphere, the distribution of wind direction is disjunct and multi-modal. Moreover, for a number of practical situations, wind direction is a time series and its dependence on time provides very important information for modeling. Our model takes these two points into account to give an accurate prediction of this kind of wind direction. A simulation study shows that our model has a significantly higher prediction accuracy and a smaller mean circular prediction error than three existing models and it is illustrated to be effective by analyzing real data. Supplementary materials accompanying this paper appear online.

AB - In this paper, a Markov-switching linked autoregressive model is proposed to describe and forecast non-continuous wind direction data. Due to the influence factors of geography and atmosphere, the distribution of wind direction is disjunct and multi-modal. Moreover, for a number of practical situations, wind direction is a time series and its dependence on time provides very important information for modeling. Our model takes these two points into account to give an accurate prediction of this kind of wind direction. A simulation study shows that our model has a significantly higher prediction accuracy and a smaller mean circular prediction error than three existing models and it is illustrated to be effective by analyzing real data. Supplementary materials accompanying this paper appear online.

KW - Circular regressive model

KW - Mean circular prediction error

KW - Non-continuous wind direction

KW - Prediction accuracy

UR - http://www.scopus.com/inward/record.url?scp=85050243900&partnerID=8YFLogxK

U2 - 10.1007/s13253-018-0331-z

DO - 10.1007/s13253-018-0331-z

M3 - Article

VL - 23

SP - 410

EP - 425

JO - Journal of Agricultural, Biological, and Environmental Statistics

JF - Journal of Agricultural, Biological, and Environmental Statistics

SN - 1085-7117

IS - 3

ER -